A Silent Speech Decoding System from EEG and EMG with Heterogenous Electrode Configurations
This work addresses the problem of developing practical silent speech decoding systems for speech-impaired patients, though it is incremental as it builds on existing methods with multi-task training.
The study tackled silent speech decoding from EEG/EMG with heterogeneous electrode setups by introducing neural networks that handle varied placements, achieving word classification accuracies of 95.3% in healthy participants and 54.5% in a speech-impaired patient, substantially outperforming single-subject models.
Silent speech decoding, which performs unvocalized human speech recognition from electroencephalography/electromyography (EEG/EMG), increases accessibility for speech-impaired humans. However, data collection is difficult and performed using varying experimental setups, making it nontrivial to collect a large, homogeneous dataset. In this study we introduce neural networks that can handle EEG/EMG with heterogeneous electrode placements and show strong performance in silent speech decoding via multi-task training on large-scale EEG/EMG datasets. We achieve improved word classification accuracy in both healthy participants (95.3%), and a speech-impaired patient (54.5%), substantially outperforming models trained on single-subject data (70.1% and 13.2%). Moreover, our models also show gains in cross-language calibration performance. This increase in accuracy suggests the feasibility of developing practical silent speech decoding systems, particularly for speech-impaired patients.